© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 53773
    Prev
    Next
    INDEX
    Explanations

    names or references to "Rodney."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ãĥIJãĥ¼
    -0.07
    nable
    -0.07
    pent
    -0.07
    \widgets
    -0.06
    zhou
    -0.06
    æľį
    -0.06
    itious
    -0.06
    оза
    -0.06
    rieb
    -0.06
    ingly
    -0.06
    POSITIVE LOGITS
    velt
    0.08
    ders
    0.08
    ding
    0.08
    èĪį
    0.08
    yssey
    0.08
    خاÙĨÙĩ
    0.08
    heck
    0.08
    sher
    0.07
    well
    0.07
    ded
    0.07
    Activations Density 0.007%

    No Known Activations